crawlrs 0.2.0

crawlrs - Enterprise-grade web scraping and crawling platform built with Rust
Documentation
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
// Copyright (c) 2025-2026 Kirky.X🌠
// SPDX-License-Identifier: Apache-2.0

use crate::utils::text_processing::encoding::{TextEncodingError, TextEncodingProcessor};
use async_trait::async_trait;
use log::{debug, error, info};

use crate::i18n::{tr_log, tr_log_args};
use regex::Regex;
use std::collections::HashMap;
use std::sync::Arc;
use std::time::{Duration, Instant};
use thiserror::Error;

/// 文本处理错误类型
#[derive(Error, Debug)]
pub enum TextProcessingError {
    #[error("Regex compilation failed: {0}")]
    RegexCompilationError(String),

    #[error("Encoding error: {0}")]
    EncodingError(#[from] TextEncodingError),
}

/// 常量定义 - 编码检测模式键名
const ENCODING_PATTERN_HTML_META: &str = "html_meta";
const ENCODING_PATTERN_XML_DECLARATION: &str = "xml_declaration";
const ENCODING_PATTERN_HTTP_CONTENT_TYPE: &str = "http_content_type";

/// 初始化编码检测正则表达式模式(公共函数,消除重复代码)
///
/// 此函数被 WebContentProcessorComponent 和 WebContentProcessor 共用
pub fn init_encoding_patterns() -> Result<HashMap<&'static str, Regex>, TextProcessingError> {
    let mut patterns = HashMap::with_capacity(4);

    patterns.insert(
        ENCODING_PATTERN_HTML_META,
        Regex::new(r#"(?i)<meta[^>]*charset\s*=\s*["']?([^"'>\s]+)["']?[^>]*>"#)
            .map_err(|e| TextProcessingError::RegexCompilationError(e.to_string()))?,
    );
    patterns.insert(
        ENCODING_PATTERN_XML_DECLARATION,
        Regex::new(r#"(?i)<\?xml[^>]*encoding\s*=\s*["']?([^"'>\s]+)["']?[^>]*\?>"#)
            .map_err(|e| TextProcessingError::RegexCompilationError(e.to_string()))?,
    );
    patterns.insert(
        ENCODING_PATTERN_HTTP_CONTENT_TYPE,
        Regex::new(r#"(?i)charset\s*=\s*([^;\s]+)"#)
            .map_err(|e| TextProcessingError::RegexCompilationError(e.to_string()))?,
    );
    Ok(patterns)
}

/// 检测文本内容是否为 HTML 结构
///
/// 用于判断内容是否包含 HTML 标签
pub fn detect_html_structure(content: &str) -> bool {
    content.contains("<html")
        || content.contains("<!DOCTYPE")
        || content.contains("<head")
        || content.contains("<body")
        || content.contains("<div")
        || content.contains("<p>")
        || content.contains("<a ")
}

/// 文本编码处理器 trait(支持 DI)
#[async_trait]
pub trait TextEncodingProcessorTrait: Send + Sync {
    fn process_text(&self, content: &[u8]) -> Result<String, TextEncodingError>;
    fn trim_newlines(&self, text: &str) -> String;
}

/// 默认文本编码处理器(基于 TextEncodingProcessor)
struct DefaultTextEncodingProcessor;

impl TextEncodingProcessorTrait for DefaultTextEncodingProcessor {
    fn process_text(&self, content: &[u8]) -> Result<String, TextEncodingError> {
        TextEncodingProcessor::new().process_text(content)
    }

    fn trim_newlines(&self, text: &str) -> String {
        text.lines().map(|l| l.trim()).collect::<Vec<_>>().join(" ")
    }
}

/// 网页内容处理器 trait(支持 DI)
///
/// 提供网页内容处理的抽象接口,便于测试时注入 mock 实现。
#[async_trait]
pub trait WebContentProcessorTrait: Send + Sync {
    fn process_web_content(
        &self,
        content: &[u8],
        content_type: Option<&str>,
    ) -> Result<ProcessedWebContent, WebContentError>;
    fn process_batch(
        &self,
        contents: Vec<(&[u8], Option<&str>)>,
    ) -> Vec<Result<ProcessedWebContent, WebContentError>>;
}

/// 网页内容处理器组件(DI 实现)
pub struct WebContentProcessorComponent {
    /// 文本编码处理器
    text_processor: Arc<dyn TextEncodingProcessorTrait>,
    /// 编码模式
    encoding_patterns: HashMap<&'static str, Regex>,
    /// HTML 清理器
    html_cleaner: HtmlCleaner,
}

impl WebContentProcessorComponent {
    pub fn new(text_processor: Arc<dyn TextEncodingProcessorTrait>) -> Self {
        Self {
            text_processor,
            encoding_patterns: init_encoding_patterns()
                .expect("Failed to initialize encoding patterns"),
            html_cleaner: HtmlCleaner::new(),
        }
    }
}

impl Default for WebContentProcessorComponent {
    fn default() -> Self {
        Self::new(Arc::new(DefaultTextEncodingProcessor))
    }
}

impl WebContentProcessorTrait for WebContentProcessorComponent {
    fn process_web_content(
        &self,
        content: &[u8],
        content_type: Option<&str>,
    ) -> Result<ProcessedWebContent, WebContentError> {
        let text_content = self.process_encoding(content)?;
        let is_html = self.detect_html_structure(&text_content);
        let declared_encoding = self.extract_declared_encoding(&text_content);
        debug!(
            "{}",
            tr_log_args(
                "text-html-structure-detected",
                &[
                    ("is_html", is_html.to_string()),
                    (
                        "encoding",
                        declared_encoding
                            .clone()
                            .unwrap_or_else(|| "none".to_string())
                            .to_string()
                    ),
                ],
            )
        );
        let extracted_text = if is_html {
            self.extract_text_from_html(&text_content)?
        } else {
            text_content.clone()
        };
        let cleaned_text = self.clean_text(&extracted_text);
        let detected_language = self.detect_language(&cleaned_text);
        Ok(ProcessedWebContent {
            original_content: text_content,
            extracted_text: cleaned_text,
            is_html,
            declared_encoding,
            detected_language,
            content_type: content_type.map(|s| s.to_string()),
            content_length: content.len(),
        })
    }

    fn process_batch(
        &self,
        contents: Vec<(&[u8], Option<&str>)>,
    ) -> Vec<Result<ProcessedWebContent, WebContentError>> {
        contents
            .into_iter()
            .map(|(content, content_type)| self.process_web_content(content, content_type))
            .collect()
    }
}

impl WebContentProcessorComponent {
    fn process_encoding(&self, content: &[u8]) -> Result<String, WebContentError> {
        match self.text_processor.process_text(content) {
            Ok(text) => {
                debug!("{}", tr_log("text-encoding-succeeded"));
                Ok(text)
            }
            Err(e) => {
                error!(
                    "{}",
                    tr_log_args("text-encoding-failed", &[("error", e.to_string())],)
                );
                Err(WebContentError::EncodingError(e))
            }
        }
    }

    fn detect_html_structure(&self, content: &str) -> bool {
        content.contains("<html")
            || content.contains("<!DOCTYPE")
            || content.contains("<head")
            || content.contains("<body")
            || content.contains("<div")
            || content.contains("<p>")
            || content.contains("<a ")
    }

    fn extract_declared_encoding(&self, content: &str) -> Option<String> {
        if let Some(captures) = self.encoding_patterns.get("html_meta")?.captures(content) {
            if let Some(encoding) = captures.get(1) {
                return Some(encoding.as_str().to_lowercase());
            }
        }
        if let Some(captures) = self
            .encoding_patterns
            .get("xml_declaration")?
            .captures(content)
        {
            if let Some(encoding) = captures.get(1) {
                return Some(encoding.as_str().to_lowercase());
            }
        }
        None
    }

    fn extract_text_from_html(&self, html: &str) -> Result<String, WebContentError> {
        self.html_cleaner.extract_text(html)
    }

    fn clean_text(&self, text: &str) -> String {
        let mut cleaned = text.to_string();
        cleaned = html_escape::decode_html_entities(&cleaned).to_string();
        cleaned = cleaned
            .chars()
            .filter(|c| !c.is_control() || c.is_whitespace())
            .collect();
        cleaned = self.text_processor.trim_newlines(&cleaned);
        cleaned.trim().to_string()
    }

    fn detect_language(&self, text: &str) -> Option<String> {
        if text.is_empty() {
            return None;
        }
        let char_count = text.chars().count() as f32;
        let chinese_ratio = text
            .chars()
            .filter(|c| {
                let code = *c as u32;
                (0x4E00..=0x9FFF).contains(&code)
                    || (0x3400..=0x4DBF).contains(&code)
                    || (0xF900..=0xFAFF).contains(&code)
            })
            .count() as f32
            / char_count;
        if chinese_ratio > 0.3 {
            Some("zh".to_string())
        } else if text.chars().filter(|c| c.is_ascii()).count() as f32 / char_count > 0.8 {
            Some("en".to_string())
        } else {
            Some("unknown".to_string())
        }
    }
}

/// 网页内容处理器
#[derive(Clone)]
pub struct WebContentProcessor {
    text_processor: Arc<TextEncodingProcessor>,
    html_cleaner: HtmlCleaner,
    encoding_patterns: HashMap<&'static str, Regex>,
}

impl Default for WebContentProcessor {
    fn default() -> Self {
        Self::new()
    }
}

impl WebContentProcessor {
    /// Create a new WebContentProcessor with default TextEncodingProcessor
    pub fn new() -> Self {
        Self::with_text_processor(TextEncodingProcessor::new())
    }

    /// Create a WebContentProcessor with a specific TextEncodingProcessor (for DI)
    pub fn with_text_processor(text_processor: TextEncodingProcessor) -> Self {
        Self {
            text_processor: Arc::new(text_processor),
            html_cleaner: HtmlCleaner::new(),
            encoding_patterns: init_encoding_patterns()
                .expect("Failed to initialize encoding patterns"),
        }
    }

    /// Create a WebContentProcessor with an injected TextEncodingProcessor
    pub fn with_injected_processor(text_processor: Arc<TextEncodingProcessor>) -> Self {
        Self {
            text_processor,
            html_cleaner: HtmlCleaner::new(),
            encoding_patterns: init_encoding_patterns()
                .expect("Failed to initialize encoding patterns"),
        }
    }

    pub fn process_web_content(
        &self,
        content: &[u8],
        content_type: Option<&str>,
    ) -> Result<ProcessedWebContent, WebContentError> {
        info!(
            "{}",
            tr_log_args(
                "text-web-content-started",
                &[("size", content.len().to_string())],
            )
        );
        let text_content = self.process_encoding(content)?;
        let is_html = self.detect_html_structure(&text_content);
        let declared_encoding = self.extract_declared_encoding(&text_content);
        debug!(
            "{}",
            tr_log_args(
                "text-html-structure-detected",
                &[
                    ("is_html", is_html.to_string()),
                    (
                        "encoding",
                        declared_encoding
                            .clone()
                            .unwrap_or_else(|| "none".to_string())
                            .to_string()
                    ),
                ],
            )
        );
        let extracted_text = if is_html {
            self.extract_text_from_html(&text_content)?
        } else {
            text_content.clone()
        };
        let cleaned_text = self.clean_text(&extracted_text);
        let detected_language = self.detect_language(&cleaned_text);
        Ok(ProcessedWebContent {
            original_content: text_content,
            extracted_text: cleaned_text,
            is_html,
            declared_encoding,
            detected_language,
            content_type: content_type.map(|s| s.to_string()),
            content_length: content.len(),
        })
    }

    fn process_encoding(&self, content: &[u8]) -> Result<String, WebContentError> {
        match self.text_processor.process_text(content) {
            Ok(text) => {
                debug!("{}", tr_log("text-encoding-succeeded"));
                Ok(text)
            }
            Err(e) => {
                error!(
                    "{}",
                    tr_log_args("text-encoding-failed", &[("error", e.to_string())],)
                );
                Err(WebContentError::EncodingError(e))
            }
        }
    }

    fn detect_html_structure(&self, content: &str) -> bool {
        content.contains("<html")
            || content.contains("<!DOCTYPE")
            || content.contains("<head")
            || content.contains("<body")
            || content.contains("<div")
            || content.contains("<p>")
            || content.contains("<a ")
    }

    fn extract_declared_encoding(&self, content: &str) -> Option<String> {
        if let Some(captures) = self.encoding_patterns.get("html_meta")?.captures(content) {
            if let Some(encoding) = captures.get(1) {
                return Some(encoding.as_str().to_lowercase());
            }
        }
        if let Some(captures) = self
            .encoding_patterns
            .get("xml_declaration")?
            .captures(content)
        {
            if let Some(encoding) = captures.get(1) {
                return Some(encoding.as_str().to_lowercase());
            }
        }
        None
    }

    fn extract_text_from_html(&self, html: &str) -> Result<String, WebContentError> {
        self.html_cleaner.extract_text(html)
    }

    fn clean_text(&self, text: &str) -> String {
        let mut cleaned = text.to_string();
        cleaned = html_escape::decode_html_entities(&cleaned).to_string();
        cleaned = cleaned
            .chars()
            .filter(|c| !c.is_control() || c.is_whitespace())
            .collect();
        cleaned = self.text_processor.trim_newlines(&cleaned);
        cleaned.trim().to_string()
    }

    fn detect_language(&self, text: &str) -> Option<String> {
        if text.is_empty() {
            return None;
        }
        let char_count = text.chars().count() as f32;
        let chinese_ratio = text
            .chars()
            .filter(|c| {
                let code = *c as u32;
                (0x4E00..=0x9FFF).contains(&code)
                    || (0x3400..=0x4DBF).contains(&code)
                    || (0xF900..=0xFAFF).contains(&code)
            })
            .count() as f32
            / char_count;
        if chinese_ratio > 0.3 {
            Some("zh".to_string())
        } else if text.chars().filter(|c| c.is_ascii()).count() as f32 / char_count > 0.8 {
            Some("en".to_string())
        } else {
            Some("unknown".to_string())
        }
    }

    pub fn process_batch(
        &self,
        contents: Vec<(&[u8], Option<&str>)>,
    ) -> Vec<Result<ProcessedWebContent, WebContentError>> {
        contents
            .into_iter()
            .map(|(content, content_type)| self.process_web_content(content, content_type))
            .collect()
    }
}

#[derive(Clone)]
pub struct HtmlCleaner {
    script_regex: Regex,
    style_regex: Regex,
    comment_regex: Regex,
    tag_regex: Regex,
    whitespace_regex: Regex,
}

impl HtmlCleaner {
    fn new() -> Self {
        Self {
            script_regex: Regex::new(r#"(?is)<script[^>]*>.*?</script>"#)
                .expect("Failed to compile script regex"),
            style_regex: Regex::new(r#"(?is)<style[^>]*>.*?</style>"#)
                .expect("Failed to compile style regex"),
            comment_regex: Regex::new(r#"(?is)<!--.*?-->"#)
                .expect("Failed to compile comment regex"),
            tag_regex: Regex::new(r#"(?is)<[^>]+>"#).expect("Failed to compile tag regex"),
            whitespace_regex: Regex::new(r#"\s+"#).expect("Failed to compile whitespace regex"),
        }
    }

    fn extract_text(&self, html: &str) -> Result<String, WebContentError> {
        let mut text = html.to_string();
        text = self.script_regex.replace_all(&text, "").to_string();
        text = self.style_regex.replace_all(&text, "").to_string();
        text = self.comment_regex.replace_all(&text, "").to_string();
        text = self.tag_regex.replace_all(&text, " ").to_string();
        text = self.normalize_whitespace(&text);
        Ok(text.trim().to_string())
    }

    fn normalize_whitespace(&self, text: &str) -> String {
        self.whitespace_regex.replace_all(text, " ").to_string()
    }
}

#[derive(Debug, Clone)]
pub struct ProcessedWebContent {
    pub original_content: String,
    pub extracted_text: String,
    pub is_html: bool,
    pub declared_encoding: Option<String>,
    pub detected_language: Option<String>,
    pub content_type: Option<String>,
    pub content_length: usize,
}

#[derive(Debug, thiserror::Error)]
pub enum WebContentError {
    #[error("Encoding error: {0}")]
    EncodingError(#[from] TextEncodingError),
    #[error("HTML parse error: {0}")]
    HtmlParseError(String),
    #[error("Content extraction error: {0}")]
    ContentExtractionError(String),
}

/// 使用提供的处理器实例处理网页内容
pub fn process_web_content_with_processor(
    processor: &WebContentProcessor,
    content: &[u8],
    content_type: Option<&str>,
) -> Result<ProcessedWebContent, WebContentError> {
    processor.process_web_content(content, content_type)
}

/// 爬虫文本处理器
pub struct CrawlTextProcessor {
    max_processing_time: Duration,
    max_content_size: usize,
}

impl Default for CrawlTextProcessor {
    fn default() -> Self {
        Self::new()
    }
}

impl CrawlTextProcessor {
    pub fn new() -> Self {
        Self {
            max_processing_time: Duration::from_secs(30),
            max_content_size: 10 * 1024 * 1024,
        }
    }

    pub fn process_crawled_content(
        &self,
        content: &[u8],
        url: &str,
        content_type: Option<&str>,
    ) -> Result<ProcessedCrawlContent, CrawlProcessingError> {
        let start_time = Instant::now();
        let content_size = content.len();
        info!(
            "{}",
            tr_log_args(
                "text-crawl-started",
                &[("url", url.to_string()), ("size", content_size.to_string()),],
            )
        );
        if content_size > self.max_content_size {
            return Err(CrawlProcessingError::ContentTooLarge {
                size: content_size,
                max_size: self.max_content_size,
            });
        }
        if start_time.elapsed() > self.max_processing_time {
            return Err(CrawlProcessingError::ProcessingTimeout);
        }
        let processed_content = self.process_content_with_timeout(content, content_type)?;
        let processing_time = start_time.elapsed();
        info!(
            "{}",
            tr_log_args(
                "text-crawl-completed",
                &[
                    ("url", url.to_string()),
                    ("elapsed", format!("{:?}", processing_time)),
                    ("length", processed_content.extracted_text.len().to_string()),
                ],
            )
        );
        Ok(ProcessedCrawlContent {
            url: url.to_string(),
            processed_content: processed_content.clone(),
            processing_time,
            original_size: content_size,
            processed_size: processed_content.extracted_text.len(),
        })
    }

    fn process_content_with_timeout(
        &self,
        content: &[u8],
        content_type: Option<&str>,
    ) -> Result<ProcessedWebContent, CrawlProcessingError> {
        use std::sync::mpsc;
        use std::thread;
        let (tx, rx) = mpsc::channel();
        let content = content.to_vec();
        let content_type = content_type.map(|s| s.to_string());
        let processor = WebContentProcessor::new();
        thread::spawn(move || {
            let result = processor.process_web_content(&content, content_type.as_deref());
            let _ = tx.send(result);
        });
        match rx.recv_timeout(self.max_processing_time) {
            Ok(result) => result.map_err(CrawlProcessingError::WebContentError),
            Err(_) => Err(CrawlProcessingError::ProcessingTimeout),
        }
    }

    pub fn process_batch(
        &self,
        batch: Vec<(&[u8], &str, Option<&str>)>,
    ) -> Vec<Result<ProcessedCrawlContent, CrawlProcessingError>> {
        let mut results = Vec::with_capacity(batch.len());
        for (content, url, content_type) in batch {
            let result = self.process_crawled_content(content, url, content_type);
            results.push(result);
        }
        results
    }

    pub fn process_simple_text(&self, text: &str) -> Result<String, CrawlProcessingError> {
        if text.is_empty() {
            return Ok(String::new());
        }
        let processor = TextEncodingProcessor::new();
        match processor.process_text(text.as_bytes()) {
            Ok(processed) => Ok(processed),
            Err(e) => Err(CrawlProcessingError::TextEncodingError(e)),
        }
    }

    pub fn validate_content_quality(&self, content: &ProcessedCrawlContent) -> ContentQuality {
        let text_length = content.processed_content.extracted_text.len();
        let word_count = content
            .processed_content
            .extracted_text
            .split_whitespace()
            .count();
        if text_length < 50 {
            return ContentQuality::Poor("Text content too short".to_string());
        }
        if word_count < 10 {
            return ContentQuality::Poor("Too few words".to_string());
        }
        let text_ratio = text_length as f64 / content.original_size as f64;
        if text_ratio < 0.01 && content.original_size > 1000 {
            return ContentQuality::Poor("Effective content ratio too low".to_string());
        }
        let repetitive_ratio =
            self.calculate_repetitive_ratio(&content.processed_content.extracted_text);
        if repetitive_ratio > 0.8 {
            return ContentQuality::Poor("Content too repetitive".to_string());
        }
        if content.processing_time.as_secs() > 10 {
            ContentQuality::Good
        } else {
            ContentQuality::Excellent
        }
    }

    fn calculate_repetitive_ratio(&self, text: &str) -> f64 {
        let words: Vec<&str> = text.split_whitespace().collect();
        if words.len() < 10 {
            return 0.0;
        }
        let mut word_counts = std::collections::HashMap::with_capacity(256);
        for word in &words {
            *word_counts.entry(word.to_lowercase()).or_insert(0) += 1;
        }
        let max_count = *word_counts.values().max().unwrap_or(&1);
        let total_words = words.len();
        (max_count as f64 / total_words as f64).min(1.0)
    }

    pub fn get_config(&self) -> CrawlProcessorConfig {
        CrawlProcessorConfig {
            max_processing_time_secs: self.max_processing_time.as_secs(),
            max_content_size_mb: self.max_content_size / (1024 * 1024),
        }
    }

    pub fn update_config(&mut self, config: CrawlProcessorConfig) {
        self.max_processing_time = Duration::from_secs(config.max_processing_time_secs);
        self.max_content_size = config.max_content_size_mb * 1024 * 1024;
        info!(
            "{}",
            tr_log_args(
                "text-config-updated",
                &[("config", format!("{:?}", config))],
            )
        );
    }
}

#[derive(Debug, Clone)]
pub struct ProcessedCrawlContent {
    pub url: String,
    pub processed_content: ProcessedWebContent,
    pub processing_time: Duration,
    pub original_size: usize,
    pub processed_size: usize,
}

#[derive(Debug, thiserror::Error)]
pub enum CrawlProcessingError {
    #[error("Text encoding processing error: {0}")]
    TextEncodingError(#[from] TextEncodingError),
    #[error("Web content processing error: {0}")]
    WebContentError(#[from] WebContentError),
    #[error("Content too large: {size} bytes (max allowed: {max_size} bytes)")]
    ContentTooLarge { size: usize, max_size: usize },
    #[error("Processing timeout")]
    ProcessingTimeout,
    #[error("Content quality too low: {0}")]
    PoorContentQuality(String),
}

#[derive(Debug, Clone, PartialEq)]
pub enum ContentQuality {
    Excellent,
    Good,
    Fair,
    Poor(String),
}

#[derive(Debug, Clone)]
pub struct CrawlProcessorConfig {
    pub max_processing_time_secs: u64,
    pub max_content_size_mb: usize,
}

impl Default for CrawlProcessorConfig {
    fn default() -> Self {
        Self {
            max_processing_time_secs: 30,
            max_content_size_mb: 10,
        }
    }
}

/// 使用提供的处理器实例处理爬取的内容
pub fn process_crawled_content_with_processor(
    processor: &CrawlTextProcessor,
    content: &[u8],
    url: &str,
    content_type: Option<&str>,
) -> Result<ProcessedCrawlContent, CrawlProcessingError> {
    processor.process_crawled_content(content, url, content_type)
}

/// 使用提供的处理器实例批量处理爬取的内容
pub fn process_crawled_batch_with_processor(
    processor: &CrawlTextProcessor,
    batch: Vec<(&[u8], &str, Option<&str>)>,
) -> Vec<Result<ProcessedCrawlContent, CrawlProcessingError>> {
    processor.process_batch(batch)
}

#[cfg(test)]
mod tests {
    use super::*;

    #[test]
    fn test_html_detection() {
        let processor = WebContentProcessor::new();
        let html_content = r#"<!DOCTYPE html><html><head><title>Test</title></head><body><p>Hello World</p></body></html>"#;
        assert!(processor.detect_html_structure(html_content));
        let plain_text = "This is plain text without any HTML tags.";
        assert!(!processor.detect_html_structure(plain_text));
    }

    #[test]
    fn test_encoding_extraction() {
        let processor = WebContentProcessor::new();
        let html_with_meta = r#"<html><head><meta charset="utf-8"><title>Test</title></head><body>Content</body></html>"#;
        let encoding = processor.extract_declared_encoding(html_with_meta);
        assert_eq!(encoding, Some("utf-8".to_string()));
    }

    #[test]
    fn test_html_text_extraction() {
        let processor = WebContentProcessor::new();
        let html_content = r#"<html><head><title>Test Page</title></head><body><h1>Main Title</h1><p>This is a <strong>test</strong> paragraph.</p><script>alert('test');</script><style>body { color: red; }</style></body></html>"#;
        let result = processor
            .process_web_content(html_content.as_bytes(), Some("text/html"))
            .unwrap();
        assert!(result.is_html);
        assert!(result.extracted_text.contains("Main Title"));
        assert!(result.extracted_text.contains("test paragraph"));
        assert!(!result.extracted_text.contains("script"));
        assert!(!result.extracted_text.contains("style"));
    }

    #[test]
    fn test_language_detection() {
        let processor = WebContentProcessor::new();
        let english_text = "This is English text content.";
        let lang = processor.detect_language(english_text);
        assert_eq!(lang, Some("en".to_string()));
        let chinese_text = "这是中文内容";
        let lang = processor.detect_language(chinese_text);
        assert_eq!(lang, Some("zh".to_string()));
    }

    #[test]
    fn test_simple_text_processing() {
        let processor = CrawlTextProcessor::new();
        let text = "Hello, 世界! This is a test.";
        let result = processor.process_simple_text(text).unwrap();
        assert_eq!(result, text);
    }

    #[test]
    fn test_repetitive_content_detection() {
        let processor = CrawlTextProcessor::new();
        let repetitive_text = "spam spam spam spam spam spam spam spam spam spam";
        let ratio = processor.calculate_repetitive_ratio(repetitive_text);
        assert!(ratio > 0.5);
        let normal_text = "This is normal text with different words and meaningful content.";
        let ratio = processor.calculate_repetitive_ratio(normal_text);
        assert!(ratio < 0.5);
    }

    // Free function tests

    #[test]
    fn test_init_encoding_patterns_returns_three_patterns() {
        let patterns = init_encoding_patterns().expect("patterns should compile");
        assert!(patterns.contains_key(ENCODING_PATTERN_HTML_META));
        assert!(patterns.contains_key(ENCODING_PATTERN_XML_DECLARATION));
        assert!(patterns.contains_key(ENCODING_PATTERN_HTTP_CONTENT_TYPE));
        assert_eq!(patterns.len(), 3);
    }

    #[test]
    fn test_init_encoding_patterns_compiles_valid_regexes() {
        let patterns = init_encoding_patterns().expect("patterns should compile");
        let html_meta = patterns.get(ENCODING_PATTERN_HTML_META).unwrap();
        assert!(html_meta.is_match(r#"<meta charset="utf-8">"#));
        let xml_decl = patterns.get(ENCODING_PATTERN_XML_DECLARATION).unwrap();
        assert!(xml_decl.is_match(r#"<?xml version="1.0" encoding="UTF-8"?>"#));
    }

    #[test]
    fn test_detect_html_structure_free_function_html_tags() {
        assert!(detect_html_structure("<html><body></body></html>"));
        assert!(detect_html_structure("<!DOCTYPE html>"));
        assert!(detect_html_structure("<head><title>X</title></head>"));
        assert!(detect_html_structure("<body>content</body>"));
        assert!(detect_html_structure("<div>content</div>"));
        assert!(detect_html_structure("<p>paragraph</p>"));
        assert!(detect_html_structure("<a href=\"x\">link</a>"));
    }

    #[test]
    fn test_detect_html_structure_free_function_non_html() {
        assert!(!detect_html_structure("plain text content"));
        assert!(!detect_html_structure("no html here at all"));
        assert!(!detect_html_structure(""));
    }

    // WebContentProcessorComponent tests

    #[test]
    fn test_web_content_processor_component_default() {
        let component = WebContentProcessorComponent::default();
        let result = component
            .process_web_content(b"plain text", Some("text/plain"))
            .unwrap();
        assert!(!result.is_html);
        assert_eq!(result.extracted_text, "plain text");
        assert_eq!(result.content_length, 10);
    }

    #[test]
    fn test_web_content_processor_component_process_html() {
        let component = WebContentProcessorComponent::default();
        let html = b"<html><body><p>Hello</p></body></html>";
        let result = component
            .process_web_content(html, Some("text/html"))
            .unwrap();
        assert!(result.is_html);
        assert!(result.extracted_text.contains("Hello"));
    }

    #[test]
    fn test_web_content_processor_component_process_batch() {
        let component = WebContentProcessorComponent::default();
        let contents = vec![
            (b"text1".as_slice(), Some("text/plain")),
            (b"<p>text2</p>".as_slice(), Some("text/html")),
            (b"text3".as_slice(), None),
        ];
        let results = component.process_batch(contents);
        assert_eq!(results.len(), 3);
        assert!(results.iter().all(|r| r.is_ok()));
        assert!(results[1].as_ref().unwrap().is_html);
    }

    #[test]
    fn test_web_content_processor_component_process_batch_empty() {
        let component = WebContentProcessorComponent::default();
        let results = component.process_batch(vec![]);
        assert!(results.is_empty());
    }

    // WebContentProcessor tests

    #[test]
    fn test_web_content_processor_default() {
        let processor = WebContentProcessor::default();
        let result = processor.process_web_content(b"hello", None).unwrap();
        assert_eq!(result.extracted_text, "hello");
    }

    #[test]
    fn test_web_content_processor_with_text_processor() {
        let processor = WebContentProcessor::with_text_processor(TextEncodingProcessor::new());
        let result = processor
            .process_web_content(b"test content", Some("text/plain"))
            .unwrap();
        assert!(!result.is_html);
        assert_eq!(result.extracted_text, "test content");
    }

    #[test]
    fn test_web_content_processor_with_injected_processor() {
        let processor =
            WebContentProcessor::with_injected_processor(Arc::new(TextEncodingProcessor::new()));
        let result = processor.process_web_content(b"injected", None).unwrap();
        assert_eq!(result.extracted_text, "injected");
    }

    #[test]
    fn test_web_content_processor_process_batch() {
        let processor = WebContentProcessor::new();
        let contents = vec![
            (b"<p>html</p>".as_slice(), Some("text/html")),
            (b"plain".as_slice(), None),
        ];
        let results = processor.process_batch(contents);
        assert_eq!(results.len(), 2);
        assert!(results[0].as_ref().unwrap().is_html);
        assert!(!results[1].as_ref().unwrap().is_html);
    }

    #[test]
    fn test_web_content_processor_detect_html_structure_all_tags() {
        let processor = WebContentProcessor::new();
        assert!(processor.detect_html_structure("<html>"));
        assert!(processor.detect_html_structure("<!DOCTYPE"));
        assert!(processor.detect_html_structure("<head"));
        assert!(processor.detect_html_structure("<body"));
        assert!(processor.detect_html_structure("<div"));
        assert!(processor.detect_html_structure("<p>"));
        assert!(processor.detect_html_structure("<a "));
        assert!(!processor.detect_html_structure("no tags here"));
    }

    #[test]
    fn test_web_content_processor_extract_declared_encoding_xml() {
        let processor = WebContentProcessor::new();
        let xml = "<?xml version=\"1.0\" encoding=\"UTF-8\"?><root/>";
        let encoding = processor.extract_declared_encoding(xml);
        assert_eq!(encoding, Some("utf-8".to_string()));
    }

    #[test]
    fn test_web_content_processor_extract_declared_encoding_meta_uppercase() {
        let processor = WebContentProcessor::new();
        let html = r#"<html><head><meta charset="UTF-8"></head></html>"#;
        let encoding = processor.extract_declared_encoding(html);
        assert_eq!(encoding, Some("utf-8".to_string()));
    }

    #[test]
    fn test_web_content_processor_extract_declared_encoding_none() {
        let processor = WebContentProcessor::new();
        let plain = "just plain text without encoding";
        let encoding = processor.extract_declared_encoding(plain);
        assert_eq!(encoding, None);
    }

    #[test]
    fn test_web_content_processor_clean_text_html_entities() {
        let processor = WebContentProcessor::new();
        let text = "Hello &amp; goodbye &lt;world&gt;";
        let cleaned = processor.clean_text(text);
        assert!(cleaned.contains("Hello & goodbye"));
        assert!(cleaned.contains("<world>"));
    }

    #[test]
    fn test_web_content_processor_clean_text_control_chars() {
        let processor = WebContentProcessor::new();
        let text = "hello\x01\x02world";
        let cleaned = processor.clean_text(text);
        assert!(!cleaned.contains('\x01'));
        assert!(!cleaned.contains('\x02'));
        assert!(cleaned.contains("hello"));
        assert!(cleaned.contains("world"));
    }

    #[test]
    fn test_web_content_processor_detect_language_empty() {
        let processor = WebContentProcessor::new();
        assert_eq!(processor.detect_language(""), None);
    }

    #[test]
    fn test_web_content_processor_detect_language_unknown() {
        let processor = WebContentProcessor::new();
        // Mix of non-ASCII and non-Chinese characters (Arabic/Cyrillic)
        let text = "Привет мир مرحبا بالعالم";
        let lang = processor.detect_language(text);
        assert_eq!(lang, Some("unknown".to_string()));
    }

    // ProcessedWebContent struct tests

    #[test]
    fn test_processed_web_content_fields() {
        let content = ProcessedWebContent {
            original_content: "original".to_string(),
            extracted_text: "extracted".to_string(),
            is_html: true,
            declared_encoding: Some("utf-8".to_string()),
            detected_language: Some("en".to_string()),
            content_type: Some("text/html".to_string()),
            content_length: 100,
        };
        assert_eq!(content.original_content, "original");
        assert_eq!(content.extracted_text, "extracted");
        assert!(content.is_html);
        assert_eq!(content.declared_encoding.as_deref(), Some("utf-8"));
        assert_eq!(content.detected_language.as_deref(), Some("en"));
        assert_eq!(content.content_type.as_deref(), Some("text/html"));
        assert_eq!(content.content_length, 100);
    }

    #[test]
    fn test_processed_web_content_clone() {
        let content = ProcessedWebContent {
            original_content: "orig".to_string(),
            extracted_text: "ext".to_string(),
            is_html: false,
            declared_encoding: None,
            detected_language: None,
            content_type: None,
            content_length: 5,
        };
        let cloned = content.clone();
        assert_eq!(cloned.extracted_text, content.extracted_text);
        assert_eq!(cloned.is_html, content.is_html);
    }

    // WebContentError variants tests

    #[test]
    fn test_web_content_error_display_encoding() {
        let err =
            WebContentError::EncodingError(TextEncodingError::DetectionFailed("test".to_string()));
        assert!(err.to_string().contains("Encoding error"));
    }

    #[test]
    fn test_web_content_error_display_html_parse() {
        let err = WebContentError::HtmlParseError("parse issue".to_string());
        assert!(err.to_string().contains("HTML parse error"));
    }

    #[test]
    fn test_web_content_error_display_content_extraction() {
        let err = WebContentError::ContentExtractionError("extract fail".to_string());
        assert!(err.to_string().contains("Content extraction error"));
    }

    // CrawlTextProcessor tests

    #[test]
    fn test_crawl_text_processor_default() {
        let processor = CrawlTextProcessor::default();
        let config = processor.get_config();
        assert_eq!(config.max_processing_time_secs, 30);
        assert_eq!(config.max_content_size_mb, 10);
    }

    #[test]
    fn test_crawl_text_processor_new() {
        let processor = CrawlTextProcessor::new();
        let config = processor.get_config();
        assert_eq!(config.max_processing_time_secs, 30);
        assert_eq!(config.max_content_size_mb, 10);
    }

    #[test]
    fn test_crawl_text_processor_get_config() {
        let processor = CrawlTextProcessor::new();
        let config = processor.get_config();
        assert_eq!(config.max_processing_time_secs, 30);
        assert_eq!(config.max_content_size_mb, 10);
    }

    #[test]
    fn test_crawl_text_processor_update_config() {
        let mut processor = CrawlTextProcessor::new();
        let new_config = CrawlProcessorConfig {
            max_processing_time_secs: 60,
            max_content_size_mb: 20,
        };
        processor.update_config(new_config);
        let config = processor.get_config();
        assert_eq!(config.max_processing_time_secs, 60);
        assert_eq!(config.max_content_size_mb, 20);
    }

    #[test]
    fn test_crawl_text_processor_process_simple_text_empty() {
        let processor = CrawlTextProcessor::new();
        let result = processor.process_simple_text("").unwrap();
        assert_eq!(result, "");
    }

    #[test]
    fn test_crawl_text_processor_process_simple_text_unicode() {
        let processor = CrawlTextProcessor::new();
        let text = r"Hello \u4e16\u754c";
        let result = processor.process_simple_text(text).unwrap();
        assert_eq!(result, "Hello 世界");
    }

    #[test]
    fn test_crawl_text_processor_process_crawled_content_plain() {
        let processor = CrawlTextProcessor::new();
        let result = processor
            .process_crawled_content(b"hello world", "http://example.com", Some("text/plain"))
            .unwrap();
        assert_eq!(result.url, "http://example.com");
        assert!(!result.processed_content.is_html);
        assert_eq!(result.processed_content.extracted_text, "hello world");
        assert_eq!(result.original_size, 11);
    }

    #[test]
    fn test_crawl_text_processor_process_crawled_content_html() {
        let processor = CrawlTextProcessor::new();
        let html = b"<html><body><p>Test content here</p></body></html>";
        let result = processor
            .process_crawled_content(html, "http://example.com", Some("text/html"))
            .unwrap();
        assert!(result.processed_content.is_html);
        assert!(result
            .processed_content
            .extracted_text
            .contains("Test content"));
    }

    #[test]
    fn test_crawl_text_processor_process_crawled_content_too_large() {
        let mut processor = CrawlTextProcessor::new();
        processor.update_config(CrawlProcessorConfig {
            max_processing_time_secs: 30,
            max_content_size_mb: 0,
        });
        let content = b"this is too large";
        let result = processor.process_crawled_content(content, "http://x.com", None);
        assert!(result.is_err());
        match result.unwrap_err() {
            CrawlProcessingError::ContentTooLarge { size, max_size } => {
                assert_eq!(size, 17);
                assert_eq!(max_size, 0);
            }
            other => panic!("expected ContentTooLarge, got {:?}", other),
        }
    }

    #[test]
    fn test_crawl_text_processor_process_batch() {
        let processor = CrawlTextProcessor::new();
        let batch = vec![
            (b"content1".as_slice(), "http://a.com", Some("text/plain")),
            (
                b"<p>content2</p>".as_slice(),
                "http://b.com",
                Some("text/html"),
            ),
            (b"content3".as_slice(), "http://c.com", None),
        ];
        let results = processor.process_batch(batch);
        assert_eq!(results.len(), 3);
        assert!(results.iter().all(|r| r.is_ok()));
    }

    #[test]
    fn test_crawl_text_processor_process_batch_empty() {
        let processor = CrawlTextProcessor::new();
        let results = processor.process_batch(vec![]);
        assert!(results.is_empty());
    }

    #[test]
    fn test_validate_content_quality_excellent() {
        let processor = CrawlTextProcessor::new();
        // 使用多样化的词汇避免重复度过高
        let diverse_text = "The quick brown fox jumps over the lazy dog near the river bank. \
             Birds sing loudly in the morning while cats sleep peacefully on warm rooftops. \
             Children play games outside enjoying sunny weather with friends and neighbors.";
        let result = processor
            .process_crawled_content(diverse_text.as_bytes(), "http://example.com", None)
            .unwrap();
        let quality = processor.validate_content_quality(&result);
        match quality {
            ContentQuality::Excellent | ContentQuality::Good => {}
            other => panic!("expected Excellent or Good, got {:?}", other),
        }
    }

    #[test]
    fn test_validate_content_quality_poor_short_text() {
        let processor = CrawlTextProcessor::new();
        let result = processor
            .process_crawled_content(b"hi", "http://x.com", None)
            .unwrap();
        let quality = processor.validate_content_quality(&result);
        match quality {
            ContentQuality::Poor(msg) => {
                assert!(
                    msg.contains("too short") || msg.contains("few words"),
                    "got: {msg}"
                );
            }
            other => panic!("expected Poor, got {:?}", other),
        }
    }

    #[test]
    fn test_validate_content_quality_poor_repetitive() {
        let processor = CrawlTextProcessor::new();
        let repetitive = "word ".repeat(50);
        let result = processor
            .process_crawled_content(repetitive.as_bytes(), "http://x.com", None)
            .unwrap();
        let quality = processor.validate_content_quality(&result);
        match quality {
            ContentQuality::Poor(msg) => assert!(msg.contains("repetitive"), "got: {msg}"),
            other => panic!("expected Poor repetitive, got {:?}", other),
        }
    }

    #[test]
    fn test_calculate_repetitive_ratio_short_text() {
        let processor = CrawlTextProcessor::new();
        let ratio = processor.calculate_repetitive_ratio("few words");
        assert_eq!(ratio, 0.0);
    }

    #[test]
    fn test_calculate_repetitive_ratio_empty() {
        let processor = CrawlTextProcessor::new();
        let ratio = processor.calculate_repetitive_ratio("");
        assert_eq!(ratio, 0.0);
    }

    // ========== CrawlProcessorConfig tests ==========

    #[test]
    fn test_crawl_processor_config_default() {
        let config = CrawlProcessorConfig::default();
        assert_eq!(config.max_processing_time_secs, 30);
        assert_eq!(config.max_content_size_mb, 10);
    }

    #[test]
    fn test_crawl_processor_config_clone() {
        let config = CrawlProcessorConfig {
            max_processing_time_secs: 45,
            max_content_size_mb: 15,
        };
        let cloned = config.clone();
        assert_eq!(cloned.max_processing_time_secs, 45);
        assert_eq!(cloned.max_content_size_mb, 15);
    }

    // ========== CrawlProcessingError variants tests ==========

    #[test]
    fn test_crawl_processing_error_content_too_large_display() {
        let err = CrawlProcessingError::ContentTooLarge {
            size: 1000,
            max_size: 500,
        };
        let msg = err.to_string();
        assert!(msg.contains("1000"));
        assert!(msg.contains("500"));
    }

    #[test]
    fn test_crawl_processing_error_processing_timeout_display() {
        let err = CrawlProcessingError::ProcessingTimeout;
        assert_eq!(err.to_string(), "Processing timeout");
    }

    #[test]
    fn test_crawl_processing_error_poor_content_quality_display() {
        let err = CrawlProcessingError::PoorContentQuality("bad quality".to_string());
        assert!(err.to_string().contains("bad quality"));
    }

    // ========== ContentQuality tests ==========

    #[test]
    fn test_content_quality_variants() {
        let excellent = ContentQuality::Excellent;
        let good = ContentQuality::Good;
        let fair = ContentQuality::Fair;
        let poor = ContentQuality::Poor("reason".to_string());

        assert_eq!(excellent, ContentQuality::Excellent);
        assert_eq!(good, ContentQuality::Good);
        assert_eq!(fair, ContentQuality::Fair);
        match poor {
            ContentQuality::Poor(r) => assert_eq!(r, "reason"),
            _ => panic!("wrong variant"),
        }
    }

    #[test]
    fn test_content_quality_clone() {
        let poor = ContentQuality::Poor("test reason".to_string());
        let cloned = poor.clone();
        match cloned {
            ContentQuality::Poor(r) => assert_eq!(r, "test reason"),
            _ => panic!("wrong variant after clone"),
        }
    }

    // ========== Free function tests ==========

    #[test]
    fn test_process_web_content_with_processor_fn() {
        let processor = WebContentProcessor::new();
        let result =
            process_web_content_with_processor(&processor, b"<p>test</p>", Some("text/html"))
                .unwrap();
        assert!(result.is_html);
        assert!(result.extracted_text.contains("test"));
    }

    #[test]
    fn test_process_crawled_content_with_processor_fn() {
        let processor = CrawlTextProcessor::new();
        let result =
            process_crawled_content_with_processor(&processor, b"hello", "http://x.com", None)
                .unwrap();
        assert_eq!(result.url, "http://x.com");
        assert!(!result.processed_content.is_html);
    }

    #[test]
    fn test_process_crawled_batch_with_processor_fn() {
        let processor = CrawlTextProcessor::new();
        let batch = vec![
            (b"a".as_slice(), "http://a.com", None),
            (b"b".as_slice(), "http://b.com", None),
        ];
        let results = process_crawled_batch_with_processor(&processor, batch);
        assert_eq!(results.len(), 2);
        assert!(results.iter().all(|r| r.is_ok()));
    }

    // ========== TextProcessingError tests ==========

    #[test]
    fn test_text_processing_error_regex_compilation_display() {
        let err = TextProcessingError::RegexCompilationError("bad regex".to_string());
        assert!(err.to_string().contains("Regex compilation failed"));
        assert!(err.to_string().contains("bad regex"));
    }

    #[test]
    fn test_text_processing_error_encoding_from() {
        let encoding_err = TextEncodingError::DetectionFailed("fail".to_string());
        let err: TextProcessingError = encoding_err.into();
        assert!(matches!(err, TextProcessingError::EncodingError(_)));
    }

    // ========== HtmlCleaner integration tests ==========

    #[test]
    fn test_html_cleaner_extracts_text_with_scripts_and_styles() {
        let processor = WebContentProcessor::new();
        let html = r#"<html><head><style>body { color: red; }</style></head><body><script>alert(1);</script><p>visible text</p></body></html>"#;
        let result = processor.extract_text_from_html(html).unwrap();
        assert!(result.contains("visible text"));
        assert!(!result.contains("alert"));
        assert!(!result.contains("color"));
    }

    #[test]
    fn test_html_cleaner_removes_comments() {
        let processor = WebContentProcessor::new();
        let html = "<p>before</p><!-- this is a comment --><p>after</p>";
        let result = processor.extract_text_from_html(html).unwrap();
        assert!(!result.contains("comment"));
        assert!(result.contains("before"));
        assert!(result.contains("after"));
    }

    #[test]
    fn test_html_cleaner_normalizes_whitespace() {
        let processor = WebContentProcessor::new();
        let html = "<p>hello</p>   <p>world</p>";
        let result = processor.extract_text_from_html(html).unwrap();
        assert!(!result.contains("   "));
    }

    // ========== validate_content_quality additional tests ==========

    #[test]
    fn test_validate_content_quality_poor_low_text_ratio() {
        let processor = CrawlTextProcessor::new();
        // Create content with large original size but low text ratio.
        // Use lots of HTML tags (which get stripped) so extracted text is small
        // relative to original content.
        let mut html = String::with_capacity(2000);
        html.push_str("<html><body>");
        for _ in 0..200 {
            html.push_str("<div></div>");
        }
        html.push_str("<p>");
        html.push_str("word ");
        for _ in 0..15 {
            html.push_str("unique ");
        }
        html.push_str("</p>");
        html.push_str("</body></html>");
        let result = processor
            .process_crawled_content(html.as_bytes(), "http://x.com", Some("text/html"))
            .unwrap();
        // original_size > 1000 and text_ratio < 0.01 should trigger Poor
        let quality = processor.validate_content_quality(&result);
        match quality {
            ContentQuality::Poor(msg) => {
                // Any Poor reason is valid: short text, few words, low ratio, or repetitive
                assert!(
                    msg.contains("too short")
                        || msg.contains("few words")
                        || msg.contains("ratio")
                        || msg.contains("repetitive"),
                    "expected Poor with meaningful reason, got: {}",
                    msg
                );
            }
            other => {
                // The exact outcome depends on text ratio calculation;
                // just verify it doesn't panic
                let _ = other;
            }
        }
    }

    #[test]
    fn test_validate_content_quality_fair_not_reached() {
        // The ContentQuality::Fair variant is defined but never returned
        // by validate_content_quality. This test documents that behavior.
        let processor = CrawlTextProcessor::new();
        let text = "This is a moderately sized text with enough words to pass \
                    the minimum thresholds. It has diverse vocabulary to avoid \
                    being flagged as repetitive. The quick brown fox jumps over \
                    the lazy dog near the river bank every single day.";
        let result = processor
            .process_crawled_content(text.as_bytes(), "http://example.com", None)
            .unwrap();
        let quality = processor.validate_content_quality(&result);
        // Should be Excellent or Good, never Fair
        assert!(
            matches!(quality, ContentQuality::Excellent | ContentQuality::Good),
            "expected Excellent or Good, got {:?}",
            quality
        );
    }

    // ========== process_web_content with various content types ==========

    #[test]
    fn test_web_content_processor_process_xml_content() {
        let processor = WebContentProcessor::new();
        let xml = b"<?xml version=\"1.0\" encoding=\"UTF-8\"?><root><item>test</item></root>";
        let result = processor
            .process_web_content(xml, Some("application/xml"))
            .unwrap();
        // XML does not contain HTML tags (html, head, body, div, p, a),
        // so is_html should be false
        assert!(!result.is_html);
        // But XML declaration encoding should be detected
        assert_eq!(result.declared_encoding, Some("utf-8".to_string()));
        // Extracted text should contain the content
        assert!(result.extracted_text.contains("test"));
    }

    #[test]
    fn test_web_content_processor_process_empty_content() {
        let processor = WebContentProcessor::new();
        let result = processor.process_web_content(b"", None).unwrap();
        assert!(!result.is_html);
        assert_eq!(result.extracted_text, "");
        assert_eq!(result.content_length, 0);
        assert_eq!(result.detected_language, None);
    }

    #[test]
    fn test_web_content_processor_process_content_with_null_bytes() {
        let processor = WebContentProcessor::new();
        // Content with some bytes that might cause encoding issues
        let content = b"hello\x00world";
        let result = processor.process_web_content(content, None);
        // Should not panic; may succeed or fail depending on encoding
        let _ = result;
    }

    // ========== CrawlTextProcessor process_batch with errors ==========

    #[test]
    fn test_crawl_text_processor_process_batch_with_mixed_results() {
        let mut processor = CrawlTextProcessor::new();
        processor.update_config(CrawlProcessorConfig {
            max_processing_time_secs: 30,
            max_content_size_mb: 0,
        });
        let batch = vec![
            (b"normal content".as_slice(), "http://a.com", None),
            (b"too large content".as_slice(), "http://b.com", None),
        ];
        let results = processor.process_batch(batch);
        assert_eq!(results.len(), 2);
        // First should fail (content too large with max_size=0)
        assert!(results[0].is_err());
        assert!(results[1].is_err());
    }

    // ========== ProcessedCrawlContent tests ==========

    #[test]
    fn test_processed_crawl_content_clone() {
        let processor = CrawlTextProcessor::new();
        let result = processor
            .process_crawled_content(b"test content", "http://x.com", None)
            .unwrap();
        let cloned = result.clone();
        assert_eq!(cloned.url, result.url);
        assert_eq!(cloned.original_size, result.original_size);
        assert_eq!(cloned.processed_size, result.processed_size);
    }

    #[test]
    fn test_processed_crawl_content_debug() {
        let processor = CrawlTextProcessor::new();
        let result = processor
            .process_crawled_content(b"debug test", "http://x.com", None)
            .unwrap();
        let debug = format!("{:?}", result);
        assert!(debug.contains("ProcessedCrawlContent"));
        assert!(debug.contains("http://x.com"));
    }

    // ========== CrawlProcessingError variants ==========

    #[test]
    fn test_crawl_processing_error_text_encoding_display() {
        let err = CrawlProcessingError::TextEncodingError(TextEncodingError::DetectionFailed(
            "detect fail".to_string(),
        ));
        assert!(err.to_string().contains("Text encoding processing error"));
    }

    #[test]
    fn test_crawl_processing_error_web_content_display() {
        let err = CrawlProcessingError::WebContentError(WebContentError::HtmlParseError(
            "parse error".to_string(),
        ));
        assert!(err.to_string().contains("Web content processing error"));
    }

    // ========== WebContentProcessorComponent with injected processor ==========

    #[test]
    fn test_web_content_processor_component_with_custom_processor() {
        let text_processor: Arc<dyn TextEncodingProcessorTrait> =
            Arc::new(DefaultTextEncodingProcessor);
        let component = WebContentProcessorComponent::new(text_processor);
        let result = component
            .process_web_content(b"custom processor test", None)
            .unwrap();
        assert_eq!(result.extracted_text, "custom processor test");
    }

    #[test]
    fn test_web_content_processor_component_process_html_with_encoding() {
        let component = WebContentProcessorComponent::default();
        let html = b"<html><head><meta charset=\"utf-8\"></head><body><p>Encoded content</p></body></html>";
        let result = component
            .process_web_content(html, Some("text/html"))
            .unwrap();
        assert!(result.is_html);
        assert_eq!(result.declared_encoding, Some("utf-8".to_string()));
        assert!(result.extracted_text.contains("Encoded content"));
    }

    // ========== TextEncodingProcessorTrait implementation ==========

    #[test]
    fn test_text_encoding_processor_component_trait_object() {
        let component: Arc<dyn TextEncodingProcessorTrait> = Arc::new(DefaultTextEncodingProcessor);
        let result = component.process_text(b"trait object test").unwrap();
        assert_eq!(result, "trait object test");
        let trimmed = component.trim_newlines("line1\nline2");
        assert_eq!(trimmed, "line1 line2");
    }

    // ========== WebContentProcessorTrait implementation ==========

    #[test]
    fn test_web_content_processor_component_trait_object() {
        let component: Arc<dyn WebContentProcessorTrait> =
            Arc::new(WebContentProcessorComponent::default());
        let result = component
            .process_web_content(b"trait test", Some("text/plain"))
            .unwrap();
        assert!(!result.is_html);
        assert_eq!(result.extracted_text, "trait test");
    }

    #[test]
    fn test_web_content_processor_component_trait_process_batch() {
        let component: Arc<dyn WebContentProcessorTrait> =
            Arc::new(WebContentProcessorComponent::default());
        let contents = vec![
            (b"a".as_slice(), None),
            (b"b".as_slice(), Some("text/plain")),
        ];
        let results = component.process_batch(contents);
        assert_eq!(results.len(), 2);
        assert!(results.iter().all(|r| r.is_ok()));
    }

    // ========== Supplementary tests: boundary cases and edge paths ==========

    #[test]
    fn test_calculate_repetitive_ratio_all_same_words() {
        // All identical words: ratio should be 1.0 (max_count == total_words).
        let processor = CrawlTextProcessor::new();
        let text = "word word word word word word word word word word";
        let ratio = processor.calculate_repetitive_ratio(text);
        assert_eq!(ratio, 1.0);
    }

    #[test]
    fn test_calculate_repetitive_ratio_case_insensitive() {
        // Words are lowercased before counting, so "Word" and "word" are the same.
        let processor = CrawlTextProcessor::new();
        let text = "Word word WORD word word word word word word word";
        let ratio = processor.calculate_repetitive_ratio(text);
        assert_eq!(ratio, 1.0);
    }

    #[test]
    fn test_calculate_repetitive_ratio_exactly_ten_words() {
        // Boundary: exactly 10 words (the minimum for ratio calculation).
        let processor = CrawlTextProcessor::new();
        let text = "a b c d e f g h i j";
        let ratio = processor.calculate_repetitive_ratio(text);
        assert_eq!(ratio, 0.1, "each word appears once, ratio = 1/10");
    }

    #[test]
    fn test_calculate_repetitive_ratio_eleven_words() {
        // Just above the boundary: 11 words.
        let processor = CrawlTextProcessor::new();
        let text = "a b c d e f g h i j a";
        let ratio = processor.calculate_repetitive_ratio(text);
        assert!(
            (ratio - (2.0 / 11.0)).abs() < 0.001,
            "ratio should be 2/11, got {}",
            ratio
        );
    }

    #[test]
    fn test_validate_content_quality_text_length_boundary() {
        // Text length exactly 50 should not trigger the "too short" branch.
        let processor = CrawlTextProcessor::new();
        // 50 characters, 10 distinct words.
        let text = "aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa \
                   bb cc dd ee ff gg hh ii jj kk";
        let result = processor
            .process_crawled_content(text.as_bytes(), "http://x.com", None)
            .unwrap();
        let quality = processor.validate_content_quality(&result);
        // Should not be Poor due to short text (length >= 50, words >= 10).
        match quality {
            ContentQuality::Excellent | ContentQuality::Good => {}
            ContentQuality::Poor(msg) => {
                // May still be Poor for other reasons (e.g. repetitive),
                // but not for "文本内容过短" or "单词数量过少".
                assert!(
                    !msg.contains("过短") && !msg.contains("过少"),
                    "should not be too short/few words: {}",
                    msg
                );
            }
            ContentQuality::Fair => panic!("Fair is never returned"),
        }
    }

    #[test]
    fn test_validate_content_quality_word_count_boundary() {
        // Exactly 10 words should not trigger the "too few words" branch.
        let processor = CrawlTextProcessor::new();
        // 10 distinct words, each long enough to make text_length >= 50.
        let words: Vec<String> = (0..10).map(|i| format!("word{}", i)).collect();
        let text = words.join(" ");
        // Ensure text length >= 50.
        assert!(
            text.len() >= 50,
            "test text must be >= 50 chars, got {}",
            text.len()
        );
        let result = processor
            .process_crawled_content(text.as_bytes(), "http://x.com", None)
            .unwrap();
        let quality = processor.validate_content_quality(&result);
        match quality {
            ContentQuality::Excellent | ContentQuality::Good => {}
            ContentQuality::Poor(msg) => {
                assert!(
                    !msg.contains("过短") && !msg.contains("过少"),
                    "should not be too short/few: {}",
                    msg
                );
            }
            ContentQuality::Fair => panic!("Fair is never returned"),
        }
    }

    #[test]
    fn test_process_simple_text_with_unicode_escapes() {
        // process_simple_text should preserve unicode escape normalization
        // (delegates to TextEncodingProcessor).
        let processor = CrawlTextProcessor::new();
        let text = r"Hello \u4e16\u754c";
        let result = processor.process_simple_text(text).unwrap();
        assert!(
            result.contains("世界"),
            "unicode escapes should be normalized: got {}",
            result
        );
    }

    #[test]
    fn test_process_simple_text_with_backslash_n() {
        // A literal backslash followed by 'n' is not a unicode escape;
        // it should be preserved as-is.
        let processor = CrawlTextProcessor::new();
        let text = r"line1\nline2";
        let result = processor.process_simple_text(text).unwrap();
        assert_eq!(result, r"line1\nline2");
    }

    #[test]
    fn test_process_batch_with_one_too_large_entry() {
        // Batch with a single too-large entry should produce one error result.
        let mut processor = CrawlTextProcessor::new();
        processor.update_config(CrawlProcessorConfig {
            max_processing_time_secs: 30,
            max_content_size_mb: 0,
        });
        let batch = vec![(b"too large content here".as_slice(), "http://x.com", None)];
        let results = processor.process_batch(batch);
        assert_eq!(results.len(), 1);
        assert!(results[0].is_err());
    }

    #[test]
    fn test_update_config_with_minimum_values() {
        // Update config with minimum allowed values (1 second, 1 MB).
        let mut processor = CrawlTextProcessor::new();
        processor.update_config(CrawlProcessorConfig {
            max_processing_time_secs: 1,
            max_content_size_mb: 1,
        });
        let config = processor.get_config();
        assert_eq!(config.max_processing_time_secs, 1);
        assert_eq!(config.max_content_size_mb, 1);
    }

    #[test]
    fn test_process_crawled_content_preserves_content_type() {
        // The content_type field should be preserved in the processed result.
        let processor = CrawlTextProcessor::new();
        let result = processor
            .process_crawled_content(b"hello", "http://x.com", Some("text/plain"))
            .unwrap();
        assert_eq!(
            result.processed_content.content_type.as_deref(),
            Some("text/plain")
        );
    }

    #[test]
    fn test_process_crawled_content_with_none_content_type() {
        // content_type=None should produce None in the result.
        let processor = CrawlTextProcessor::new();
        let result = processor
            .process_crawled_content(b"hello", "http://x.com", None)
            .unwrap();
        assert!(result.processed_content.content_type.is_none());
    }

    #[test]
    fn test_processed_crawl_content_fields() {
        // Verify all fields of ProcessedCrawlContent are correctly populated.
        let processor = CrawlTextProcessor::new();
        let result = processor
            .process_crawled_content(b"test data", "http://example.com", Some("text/plain"))
            .unwrap();
        assert_eq!(result.url, "http://example.com");
        assert_eq!(result.original_size, 9);
        assert_eq!(
            result.processed_size,
            result.processed_content.extracted_text.len()
        );
        assert!(!result.processing_time.is_zero());
    }

    #[test]
    fn test_crawl_processing_error_text_encoding_from() {
        // Verify From<TextEncodingError> for CrawlProcessingError.
        let encoding_err = TextEncodingError::ConversionFailed("conv fail".to_string());
        let crawl_err: CrawlProcessingError = encoding_err.into();
        match crawl_err {
            CrawlProcessingError::TextEncodingError(_) => {}
            other => panic!("expected TextEncodingError, got {:?}", other),
        }
    }

    #[test]
    fn test_crawl_processing_error_web_content_from() {
        // Verify From<WebContentError> for CrawlProcessingError.
        let web_err = WebContentError::ContentExtractionError("extract fail".to_string());
        let crawl_err: CrawlProcessingError = web_err.into();
        match crawl_err {
            CrawlProcessingError::WebContentError(_) => {}
            other => panic!("expected WebContentError, got {:?}", other),
        }
    }

    #[test]
    fn test_crawl_processor_config_default_values() {
        // Verify the default config matches the processor's default config.
        let processor = CrawlTextProcessor::new();
        let processor_config = processor.get_config();
        let default_config = CrawlProcessorConfig::default();
        assert_eq!(
            processor_config.max_processing_time_secs,
            default_config.max_processing_time_secs
        );
        assert_eq!(
            processor_config.max_content_size_mb,
            default_config.max_content_size_mb
        );
    }

    #[test]
    fn test_content_quality_debug_format() {
        // Verify ContentQuality implements Debug.
        let excellent = ContentQuality::Excellent;
        let debug = format!("{:?}", excellent);
        assert!(debug.contains("Excellent"));
    }

    #[test]
    fn test_processed_crawl_content_debug_contains_url() {
        // The Debug output should contain the URL for traceability.
        let processor = CrawlTextProcessor::new();
        let result = processor
            .process_crawled_content(b"data", "http://trace.example.com", None)
            .unwrap();
        let debug = format!("{:?}", result);
        assert!(debug.contains("http://trace.example.com"));
    }

    #[test]
    fn test_crawl_text_processor_process_batch_preserves_order() {
        // Batch results should preserve the order of inputs.
        let processor = CrawlTextProcessor::new();
        let batch = vec![
            (b"first".as_slice(), "http://a.com", None),
            (b"second".as_slice(), "http://b.com", None),
            (b"third".as_slice(), "http://c.com", None),
        ];
        let results = processor.process_batch(batch);
        assert_eq!(results.len(), 3);
        assert_eq!(results[0].as_ref().unwrap().url, "http://a.com");
        assert_eq!(results[1].as_ref().unwrap().url, "http://b.com");
        assert_eq!(results[2].as_ref().unwrap().url, "http://c.com");
    }

    #[test]
    fn test_validate_content_quality_with_empty_extracted_text() {
        // Empty extracted text should be Poor (too short).
        let processor = CrawlTextProcessor::new();
        // Construct a ProcessedCrawlContent with empty extracted text.
        let processed = ProcessedCrawlContent {
            url: "http://x.com".to_string(),
            processed_content: ProcessedWebContent {
                original_content: String::new(),
                extracted_text: String::new(),
                is_html: false,
                declared_encoding: None,
                detected_language: None,
                content_type: None,
                content_length: 0,
            },
            processing_time: std::time::Duration::from_millis(1),
            original_size: 0,
            processed_size: 0,
        };
        let quality = processor.validate_content_quality(&processed);
        match quality {
            ContentQuality::Poor(msg) => assert!(msg.contains("too short")),
            other => panic!("expected Poor (too short), got {:?}", other),
        }
    }

    #[test]
    fn test_crawl_processor_config_clone_and_debug() {
        // Verify Clone and Debug traits work for CrawlProcessorConfig.
        let config = CrawlProcessorConfig {
            max_processing_time_secs: 45,
            max_content_size_mb: 15,
        };
        let cloned = config.clone();
        assert_eq!(cloned.max_processing_time_secs, 45);
        let debug = format!("{:?}", config);
        assert!(debug.contains("45"));
    }

    #[test]
    fn test_web_content_processor_clean_text_trims_whitespace() {
        // clean_text should trim leading/trailing whitespace.
        let processor = WebContentProcessor::new();
        let cleaned = processor.clean_text("  hello  ");
        assert_eq!(cleaned, "hello");
    }

    #[test]
    fn test_web_content_processor_clean_text_preserves_inner_whitespace() {
        // Inner whitespace should be normalized but not removed.
        let processor = WebContentProcessor::new();
        let cleaned = processor.clean_text("hello   world");
        // trim_newlines joins lines with space; multiple spaces may be preserved
        // or collapsed depending on the path. Verify it contains both words.
        assert!(cleaned.contains("hello"));
        assert!(cleaned.contains("world"));
    }

    #[test]
    fn test_html_cleaner_extract_text_from_empty_html() {
        // Empty HTML should produce empty text.
        let processor = WebContentProcessor::new();
        let result = processor.extract_text_from_html("").unwrap();
        assert_eq!(result, "");
    }

    #[test]
    fn test_html_cleaner_extract_text_only_tags() {
        // HTML with only tags (no text content) should produce empty/whitespace.
        let processor = WebContentProcessor::new();
        let result = processor
            .extract_text_from_html("<div></div><span></span>")
            .unwrap();
        assert!(result.trim().is_empty());
    }

    #[test]
    fn test_web_content_processor_process_web_content_with_meta_charset() {
        // HTML with meta charset should detect the encoding and extract text.
        let processor = WebContentProcessor::new();
        let html = b"<html><head><meta charset=\"utf-8\"><title>Test</title></head><body><p>Content</p></body></html>";
        let result = processor
            .process_web_content(html, Some("text/html"))
            .unwrap();
        assert!(result.is_html);
        assert_eq!(result.declared_encoding, Some("utf-8".to_string()));
        assert!(result.extracted_text.contains("Content"));
    }

    // ========== 超时路径测试 ==========
    // 覆盖 process_crawled_content 的 near-dead timeout 检查(行 540-542)
    // 和 process_content_with_timeout 的 recv_timeout 超时分支(行 575-578)

    #[test]
    fn test_process_crawled_content_near_dead_timeout_with_zero_max_time() {
        // 设置 max_processing_time_secs=0,start_time.elapsed() > Duration::ZERO
        // 几乎立即为 true,触发 near-dead timeout 检查。
        let mut processor = CrawlTextProcessor::new();
        processor.update_config(CrawlProcessorConfig {
            max_processing_time_secs: 0,
            max_content_size_mb: 10,
        });
        let content = b"hello world";
        let result = processor.process_crawled_content(content, "http://x.com", None);
        assert!(
            result.is_err(),
            "should fail with ProcessingTimeout when max_processing_time is zero"
        );
        match result.unwrap_err() {
            CrawlProcessingError::ProcessingTimeout => {}
            other => panic!("expected ProcessingTimeout, got {:?}", other),
        }
    }

    #[test]
    fn test_process_crawled_content_near_dead_timeout_with_html_content() {
        // near-dead timeout with HTML content(验证 content_size 检查通过后触发 timeout)
        let mut processor = CrawlTextProcessor::new();
        processor.update_config(CrawlProcessorConfig {
            max_processing_time_secs: 0,
            max_content_size_mb: 10,
        });
        let html = b"<html><body><p>test content</p></body></html>";
        let result = processor.process_crawled_content(html, "http://x.com", Some("text/html"));
        assert!(result.is_err());
        match result.unwrap_err() {
            CrawlProcessingError::ProcessingTimeout => {}
            other => panic!("expected ProcessingTimeout, got {:?}", other),
        }
    }

    // ========== WebContentProcessorComponent detect_language 覆盖 ==========

    #[test]
    fn test_web_content_processor_component_detect_language_chinese() {
        // 纯中文字符(无标点/ASCII),chinese_ratio = N/(3N) = 0.333 > 0.3 → "zh"
        let component = WebContentProcessorComponent::default();
        let chinese_text = "你好世界测试文本".as_bytes();
        let result = component
            .process_web_content(chinese_text, Some("text/plain"))
            .expect("processing Chinese text should succeed");
        assert_eq!(
            result.detected_language,
            Some("zh".to_string()),
            "pure Chinese text should be detected as zh"
        );
    }

    #[test]
    fn test_web_content_processor_component_detect_language_unknown() {
        // 非 ASCII 非中文(西里尔字母),chinese_ratio=0, ASCII ratio<0.8 → "unknown"
        let component = WebContentProcessorComponent::default();
        let unknown_text = "Привet мир".as_bytes();
        let result = component
            .process_web_content(unknown_text, Some("text/plain"))
            .expect("processing unknown-language text should succeed");
        assert_eq!(
            result.detected_language,
            Some("unknown".to_string()),
            "non-ASCII non-Chinese text should be detected as unknown"
        );
    }

    // ========== WebContentProcessorComponent extract_declared_encoding xml_declaration 分支覆盖 ==========

    #[test]
    fn test_web_content_processor_component_extract_declared_encoding_xml() {
        // 用 WebContentProcessorComponent 处理 XML 内容(无 html meta charset),
        // 覆盖 extract_declared_encoding 的 xml_declaration 分支(行 226-227)。
        let component = WebContentProcessorComponent::default();
        let xml = b"<?xml version=\"1.0\" encoding=\"UTF-8\"?><root><item>test</item></root>";
        let result = component
            .process_web_content(xml, Some("application/xml"))
            .expect("processing XML should succeed");
        // XML 声明的 encoding 应被检测到
        assert_eq!(
            result.declared_encoding,
            Some("utf-8".to_string()),
            "XML declaration encoding should be detected"
        );
    }

    #[test]
    fn test_web_content_processor_component_extract_declared_encoding_xml_iso_8859() {
        // 另一个 XML 编码声明,确保 xml_declaration 分支对不同编码值工作。
        let component = WebContentProcessorComponent::default();
        let xml = b"<?xml version=\"1.0\" encoding=\"ISO-8859-1\"?><root/>";
        let result = component
            .process_web_content(xml, None)
            .expect("processing XML with ISO-8859-1 should succeed");
        assert_eq!(
            result.declared_encoding,
            Some("iso-8859-1".to_string()),
            "XML declaration encoding should be lowercased"
        );
    }

    // ========== WebContentProcessorComponent detect_language 空文本分支覆盖 ==========

    #[test]
    fn test_web_content_processor_component_detect_language_empty_text() {
        // 用 WebContentProcessorComponent 处理空内容,
        // clean_text 后为空字符串,覆盖 detect_language 的空文本分支(行 250)。
        let component = WebContentProcessorComponent::default();
        let result = component
            .process_web_content(b"", None)
            .expect("processing empty content should succeed");
        assert_eq!(
            result.detected_language, None,
            "empty text should return None for detected_language"
        );
        assert_eq!(result.extracted_text, "");
    }

    #[test]
    fn test_web_content_processor_component_detect_language_whitespace_only() {
        // 仅包含空白的内容,clean_text 后为空字符串,
        // 覆盖 detect_language 的空文本分支。
        let component = WebContentProcessorComponent::default();
        let result = component
            .process_web_content(b"   \n\t  ", None)
            .expect("processing whitespace-only content should succeed");
        assert_eq!(
            result.detected_language, None,
            "whitespace-only text should return None for detected_language"
        );
    }

    // ========== validate_content_quality 分支覆盖 ==========

    #[test]
    fn test_validate_content_quality_word_count_less_than_10() {
        // 构造 text_length >= 50 但 word_count < 10 的内容,
        // 覆盖 validate_content_quality 的 word_count < 10 分支(行 615)。
        let processor = CrawlTextProcessor::new();
        // 50 个 'a' 无空格:text_length=50, word_count=1
        let extracted_text = "a".repeat(50);
        let processed = ProcessedCrawlContent {
            url: "http://x.com".to_string(),
            processed_content: ProcessedWebContent {
                original_content: extracted_text.clone(),
                extracted_text,
                is_html: false,
                declared_encoding: None,
                detected_language: Some("en".to_string()),
                content_type: None,
                content_length: 50,
            },
            processing_time: std::time::Duration::from_millis(1),
            original_size: 50,
            processed_size: 50,
        };
        let quality = processor.validate_content_quality(&processed);
        match quality {
            ContentQuality::Poor(msg) => {
                assert!(
                    msg.contains("few words"),
                    "expected Poor (too few words), got: {}",
                    msg
                );
            }
            other => panic!("expected Poor (word_count < 10), got {:?}", other),
        }
    }

    #[test]
    fn test_validate_content_quality_low_text_ratio() {
        // 构造 text_length >= 50, word_count >= 10, original_size > 1000,
        // 但 text_ratio < 0.01 的内容,覆盖行 619。
        let processor = CrawlTextProcessor::new();
        // 10 个不同的单词,长度 >= 50
        let words: Vec<String> = (0..10).map(|i| format!("word{}", i)).collect();
        let extracted_text = words.join(" ");
        assert!(extracted_text.len() >= 50);
        let text_len = extracted_text.len();
        let original_size = 100_000; // 很大的 original_size
        let processed = ProcessedCrawlContent {
            url: "http://x.com".to_string(),
            processed_content: ProcessedWebContent {
                original_content: extracted_text.clone(),
                extracted_text,
                is_html: false,
                declared_encoding: None,
                detected_language: Some("en".to_string()),
                content_type: None,
                content_length: text_len,
            },
            processing_time: std::time::Duration::from_millis(1),
            original_size,
            processed_size: text_len,
        };
        let quality = processor.validate_content_quality(&processed);
        match quality {
            ContentQuality::Poor(msg) => {
                assert!(
                    msg.contains("ratio"),
                    "expected Poor (low text ratio), got: {}",
                    msg
                );
            }
            other => panic!("expected Poor (text_ratio < 0.01), got {:?}", other),
        }
    }

    #[test]
    fn test_validate_content_quality_good_when_processing_time_exceeds_10s() {
        // 构造 processing_time > 10 秒的 ProcessedCrawlContent,
        // 覆盖 validate_content_quality 的 processing_time > 10s 分支(行 627)。
        let processor = CrawlTextProcessor::new();
        // 满足前面的检查:text_length >= 50, word_count >= 10,
        // text_ratio >= 0.01, repetitive_ratio <= 0.8
        let diverse_text = "The quick brown fox jumps over the lazy dog near the river bank. \
             Birds sing loudly in the morning while cats sleep peacefully on warm rooftops. \
             Children play games outside enjoying sunny weather with friends and neighbors.";
        let text_len = diverse_text.len();
        let processed = ProcessedCrawlContent {
            url: "http://x.com".to_string(),
            processed_content: ProcessedWebContent {
                original_content: diverse_text.to_string(),
                extracted_text: diverse_text.to_string(),
                is_html: false,
                declared_encoding: None,
                detected_language: Some("en".to_string()),
                content_type: None,
                content_length: text_len,
            },
            // processing_time = 11 秒,触发 Good 分支
            processing_time: std::time::Duration::from_secs(11),
            original_size: text_len,
            processed_size: text_len,
        };
        let quality = processor.validate_content_quality(&processed);
        assert_eq!(
            quality,
            ContentQuality::Good,
            "processing_time > 10s should return Good"
        );
    }

    #[test]
    fn test_validate_content_quality_excellent_when_processing_time_under_10s() {
        // 构造 processing_time <= 10 秒的 ProcessedCrawlContent,
        // 验证返回 Excellent(与 Good 分支对比)。
        let processor = CrawlTextProcessor::new();
        let diverse_text = "The quick brown fox jumps over the lazy dog near the river bank. \
             Birds sing loudly in the morning while cats sleep peacefully on warm rooftops. \
             Children play games outside enjoying sunny weather with friends and neighbors.";
        let text_len = diverse_text.len();
        let processed = ProcessedCrawlContent {
            url: "http://x.com".to_string(),
            processed_content: ProcessedWebContent {
                original_content: diverse_text.to_string(),
                extracted_text: diverse_text.to_string(),
                is_html: false,
                declared_encoding: None,
                detected_language: Some("en".to_string()),
                content_type: None,
                content_length: text_len,
            },
            processing_time: std::time::Duration::from_secs(5),
            original_size: text_len,
            processed_size: text_len,
        };
        let quality = processor.validate_content_quality(&processed);
        assert_eq!(
            quality,
            ContentQuality::Excellent,
            "processing_time <= 10s should return Excellent"
        );
    }
}